Triple
T32979457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soviet aircraft carrier Minsk |
E843755
|
entity |
| Predicate | locationAsThemePark |
P202950
|
FINISHED |
| Object | Shenzhen |
E18299
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Shenzhen | Statement: [Soviet aircraft carrier Minsk, locationAsThemePark, Shenzhen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationAsThemePark Context triple: [Soviet aircraft carrier Minsk, locationAsThemePark, Shenzhen]
-
A.
locatedInThemeParkType
Indicates that an entity is situated within or belongs to a specific type or category of theme park.
-
B.
themeParkAttractionLocation
Indicates the specific place or area within a theme park where a particular attraction is situated.
-
C.
locatedInAmusementPark
chosen
Indicates that one entity is situated within or is part of an amusement park.
-
D.
countryParkLocatedOn
Indicates that a country park is situated on or within the area of a specified geographic feature or land unit.
-
E.
themeParkPresence
Indicates that an entity is present at, located in, or associated with a theme park in the context of a given event or situation.
- F. None of above.
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f3494c6f9c8190a255409fce8b1d3b |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a034af7066c81908719bff353d77b16 |
completed | May 12, 2026, 3:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37cfc8544c819084e3e45070df3de7 |
completed | June 21, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_6a034a2fc2308190b0b8fbd458a39323 |
completed | May 12, 2026, 3:41 p.m. |
Created at: May 1, 2026, 1:22 a.m.